K-way tree classification based on semi-greedy structure applied to multisource remote sensing images

Yang Lang Chang, Zhi Ming Chen, Jyh Perng Fang, Wen Yew Liang, Tung Ju Hsieh, Wei Lieh Hsu, Hsuan Ren, Kun Shan Chen

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In this paper we present a new supervised classification method, referred to as the k-way tree semi-greedy (KTSG) classifier, for the classification of multisource remote sensing images. The generalized positive Boolean function (GPBF) classifier scheme is recently proposed based on minimum classification error (MCE) criteria to improve classification performance. It makes use of MCE criteria to apply positive and negative samples as training parameters. Unfortunately, the classification performance of GPBF is limited when the number of classes increases. This is occurred in training phase by the unbalanced numbers of positive and negative samples caused by the use of a large number of classes. The proposed KTSG overcomes this drawback by modifying the scheme from the perception of pattern-node based semi-greedy (bottom-up scheme used in GPBF) to the conception of region-based semi-greedy (also known as the top-down scheme in KTSG). It is organized by a k-way tree in which every node is composed of a set of k-dimensional positive and negative labeled samples as represented as a percentage, i.e. the corresponding ratio of number of a specific (positive) class samples to the total number of the other (negative) classes. It iteratively divides the d-dimensional hyperplane into 2d subspaces according to the centroids of the labeled (training) samples of all classes. The statistical ratios between different classes are then compared as a basis for stopping the new subspace separation and identifying which subspace belongs to which class. By delivering both positive and negative samples of different classes to KTSG learning modules, KTSG outperforms GPBF and traditional classifiers in terms of classification accuracies. The effectiveness of the proposed KTSG is evaluated by fusing MODIS/ASTER airborne simulator (MASTER) hyperspectral images and airborne synthetic aperture radar (AIRSAR) images for land cover classification during the Pacrim II campaign.

Original languageEnglish
Title of host publication2009 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2009 - Proceedings
PagesIII979-III982
DOIs
StatePublished - 2009
Event2009 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2009 - Cape Town, South Africa
Duration: 12 Jul 200917 Jul 2009

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume3

Conference

Conference2009 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2009
Country/TerritorySouth Africa
CityCape Town
Period12/07/0917/07/09

Fingerprint

Dive into the research topics of 'K-way tree classification based on semi-greedy structure applied to multisource remote sensing images'. Together they form a unique fingerprint.

Cite this